_index.org

Social Learning

Last edited: August 8, 2025

Social Learning is the property of learning with other agents in your environment.

  • learning from feedback
  • human ai coordination
  • social learning
  • adversarial training

Social Network

Last edited: August 8, 2025

A Social Network is a scheme for studying the relationships and interactions amongst groups of people.

  • people: \(V\)
  • relationship: \(E\)
  • system: a network \(G(V,E)\)

Importantly, the “labels” of \(E\) often do not matter as we frequently want to study only the graphical structure of the Social Network.

degree (node)

The degree of a node is the number of edges that are touching that node (whether in or out, or undirected).

The in-degree and out-degree are the number of edges touching that node (going in or out) respectively.

Social Reinforcement Learning

Last edited: August 8, 2025

Key question: can multi-agent optimization problems help reinforcement learning stuff

using deep RL for combinatorial optimiazation

  • fast inference scals well with instance size
  • maybe difficult to actually discover optimal solution: high sample complexity, or failing to find good solutions
  • doesn’t generalize well

why multi-agent works

  • decentralized training to improve sample efficiency
  • adversarial training

New Concepts

Important Results / Claims

Social Security Administration

Last edited: August 8, 2025

Social Security Administration is a welfare program to directly give cash to those who are in need.

softmax

Last edited: August 8, 2025

\begin{equation} softmax\qty(x_{i}) = \frac{\exp(x_{i})}{\sum_{j=1}^{n} \exp(x_{j})} \end{equation}

its “softmax”!

  • max: amplifies the probability of the largest \(x_{i}\)
  • soft: because it assign some probability to smaller \(x_{j}\) as well